Reinforcement learning Based Automated Design of Differential Evolution Algorithm for Black-box Optimization
This work addresses the problem of algorithm selection and tuning for black-box optimization, which is incremental as it builds on existing DE enhancements with a novel meta-learning approach.
The paper tackles the challenge of no single differential evolution variant being universally superior for black-box optimization by introducing a reinforcement learning framework to automatically design customized DE configurations, achieving promising results in benchmarks against state-of-the-art algorithms.
Differential evolution (DE) algorithm is recognized as one of the most effective evolutionary algorithms, demonstrating remarkable efficacy in black-box optimization due to its derivative-free nature. Numerous enhancements to the fundamental DE have been proposed, incorporating innovative mutation strategies and sophisticated parameter tuning techniques to improve performance. However, no single variant has proven universally superior across all problems. To address this challenge, we introduce a novel framework that employs reinforcement learning (RL) to automatically design DE for black-box optimization through meta-learning. RL acts as an advanced meta-optimizer, generating a customized DE configuration that includes an optimal initialization strategy, update rule, and hyperparameters tailored to a specific black-box optimization problem. This process is informed by a detailed analysis of the problem characteristics. In this proof-of-concept study, we utilize a double deep Q-network for implementation, considering a subset of 40 possible strategy combinations and parameter optimizations simultaneously. The framework's performance is evaluated against black-box optimization benchmarks and compared with state-of-the-art algorithms. The experimental results highlight the promising potential of our proposed framework.